Automated pull request reviews for security, logic, and style consistency across multiple languages.
Claude (Anthropic) and Tool Calling Skills
11 skills match Claude (Anthropic) plus Tool Calling. Clear filters
The Agent Skill Source directory is architected into three primary discovery layers: Outcome-based Categories (what you want to achieve), Runtime Compatibility (where the agent runs), and Execution Strategy (how the skill is processed). To find the most reliable capabilities, use the Highest Rated sort and filter by Verified trust levels.
Search results
Real-time security audit skill scanning for OWASP Top 10 vulnerabilities and infrastructure misconfigurations.
Local text-to-speech conversion using sherpa-onnx, enabling offline and private TTS functionality without relying on cloud services.
A comprehensive guide to using Claude's Skills feature for document generation, data analysis, and business automation.
Enables AI agents to interact with Discord channels, send messages, react, edit, delete, poll, manage threads, search content, and set presence.
Control Slack from OpenClaw to react to messages, manage pins, send/edit messages, and fetch member info. Requires configured bot token.
A comprehensive tutorial series on building sophisticated general-purpose AI agents using the Claude Agent SDK, from basic research to multi-agent orchestration.
This skill provides a comprehensive, structured workflow designed to guide users through the collaborative creation of various structured documents, including technical specifications, proposals, decision documents, a...
Provides a continuous, curated narrative of an AI agent's daily work, technical insights, and growth.
Automate Mixpanel tasks like events, segmentation, funnels, cohorts, and user profiles using Rube MCP (Composio). Always search tools first.
Orchestrates AI agents for sophisticated debugging and automated resolution of production issues using modern AI tools and observability platforms.
Other ways into the directory
Filters narrow the list. These pages start you somewhere specific instead, with the context that explains what you are looking at.
Browse by runtime
Popular tags
Cannot find what you need?
Submit the GitHub repository and we will parse the SKILL.md, run the trust checks, and publish it. You keep the credit as the author.
Submit a skill